Nicolás Navarro-Guerrero

Alexander Fabisch, Wadhah Zai El Amri, Chandandeep Singh et al.

Human manipulation skills represent a pinnacle of their voluntary motor functions, requiring the coordination of many degrees of freedom and processing of high-dimensional sensor input to achieve remarkable dexterity. Thus, we set out to answer whether the human hand, with its associated biomechanical properties, sensors, and control mechanisms, is an ideal that we should strive for in robotics. Do robots need anthropomorphic hands? We start by extracting characteristics of the human hand in terms of biomechanics and perception to compare them with currently commercially available robotic hands. From this comparison, we derive our research questions that connect manipulation system complexity to skill repertoire size and dexterity. We attempt to answer these with a systematic literature review, in which we analyze the manipulation capabilities demonstrated in 125 papers from 2019-2025. Although complex five-fingered hands are often considered the ultimate goal for robotic manipulators, they are not necessary for all tasks. We find that in-hand manipulation does not benefit from anthropomorphic hand design as simpler mechanisms are sufficient, but mechanism complexity correlates with the breadth of manipulation tasks a hand can perform. Sensor integration and intelligent manipulation strategies remain underexplored, which may be because of a misalignment with hand design: instead of replicating the number of fingers and degrees of freedom, focusing on robustness and softness would allow more intelligent control and learning to exploit environmental contacts and integrate more sensors. Finally, we argue for standardized evaluation criteria to enable systematic comparison of hand designs and manipulation systems.

Nicolás Navarro-Guerrero, Sibel Toprak, Josip Josifovski et al.

The object perception capabilities of humans are impressive, and this becomes even more evident when trying to develop solutions with a similar proficiency in autonomous robots. While there have been notable advancements in the technologies for artificial vision and touch, the effective integration of these two sensory modalities in robotic applications still needs to be improved, and several open challenges exist. Taking inspiration from how humans combine visual and haptic perception to perceive object properties and drive the execution of manual tasks, this article summarises the current state of the art of visuo-haptic object perception in robots. Firstly, the biological basis of human multimodal object perception is outlined. Then, the latest advances in sensing technologies and data collection strategies for robots are discussed. Next, an overview of the main computational techniques is presented, highlighting the main challenges of multimodal machine learning and presenting a few representative articles in the areas of robotic object recognition, peripersonal space representation and manipulation. Finally, informed by the latest advancements and open challenges, this article outlines promising new research directions.

Josip Josifovski, Sayantan Auddy, Mohammadhossein Malmir et al.

Domain Randomization (DR) is commonly used for sim2real transfer of reinforcement learning (RL) policies in robotics. Most DR approaches require a simulator with a fixed set of tunable parameters from the start of the training, from which the parameters are randomized simultaneously to train a robust model for use in the real world. However, the combined randomization of many parameters increases the task difficulty and might result in sub-optimal policies. To address this problem and to provide a more flexible training process, we propose Continual Domain Randomization (CDR) for RL that combines domain randomization with continual learning to enable sequential training in simulation on a subset of randomization parameters at a time. Starting from a model trained in a non-randomized simulation where the task is easier to solve, the model is trained on a sequence of randomizations, and continual learning is employed to remember the effects of previous randomizations. Our robotic reaching and grasping tasks experiments show that the model trained in this fashion learns effectively in simulation and performs robustly on the real robot while matching or outperforming baselines that employ combined randomization or sequential randomization without continual learning. Our code and videos are available at https://continual-dr.github.io/.

Josip Josifovski, Mohammadhossein Malmir, Noah Klarmann et al.

Randomization is currently a widely used approach in Sim2Real transfer for data-driven learning algorithms in robotics. Still, most Sim2Real studies report results for a specific randomization technique and often on a highly customized robotic system, making it difficult to evaluate different randomization approaches systematically. To address this problem, we define an easy-to-reproduce experimental setup for a robotic reach-and-balance manipulator task, which can serve as a benchmark for comparison. We compare four randomization strategies with three randomized parameters both in simulation and on a real robot. Our results show that more randomization helps in Sim2Real transfer, yet it can also harm the ability of the algorithm to find a good policy in simulation. Fully randomized simulations and fine-tuning show differentiated results and translate better to the real robot than the other approaches tested.

Daniel Harnack, Julie Pivin-Bachler, Nicolás Navarro-Guerrero

Reinforcement learning (RL) has become widely adopted in robot control. Despite many successes, one major persisting problem can be very low data efficiency. One solution is interactive feedback, which has been shown to speed up RL considerably. As a result, there is an abundance of different strategies, which are, however, primarily tested on discrete grid-world and small scale optimal control scenarios. In the literature, there is no consensus about which feedback frequency is optimal or at which time the feedback is most beneficial. To resolve these discrepancies we isolate and quantify the effect of feedback frequency in robotic tasks with continuous state and action spaces. The experiments encompass inverse kinematics learning for robotic manipulator arms of different complexity. We show that seemingly contradictory reported phenomena occur at different complexity levels. Furthermore, our results suggest that no single ideal feedback frequency exists. Rather that feedback frequency should be changed as the agent's proficiency in the task increases.

Oscar Alberto Juiña Quilachamín, Nicolás Navarro-Guerrero

Tactile sensors have been developed since the early '70s and have greatly improved, but there are still no widely adopted solutions. Various technologies, such as capacitive, piezoelectric, piezoresistive, optical, and magnetic, are used in haptic sensing. However, most sensors are not mechanically robust for many applications and cannot cope well with curved or sizeable surfaces. Aiming to address this problem, we present a 3D-printed fingerprint pattern to enhance the body-borne vibration signal for dynamic tactile feedback. The 3D-printed fingerprint patterns were designed and tested for an RH8D Adult size Robot Hand. The patterns significantly increased the signal's power to over 11 times the baseline. A public haptic dataset including 52 objects of several materials was created using the best fingerprint pattern and material.

Wadhah Zai El Amri, Nicolás Navarro-Guerrero

Tactile sensing presents a promising opportunity for enhancing the interaction capabilities of today's robots. BioTac is a commonly used tactile sensor that enables robots to perceive and respond to physical tactile stimuli. However, the sensor's non-linearity poses challenges in simulating its behavior. In this paper, we first investigate a BioTac simulation that uses temperature, force, and contact point positions to predict the sensor outputs. We show that training with BioTac temperature readings does not yield accurate sensor output predictions during deployment. Consequently, we tested three alternative models, i.e., an XGBoost regressor, a neural network, and a transformer encoder. We train these models without temperature readings and provide a detailed investigation of the window size of the input vectors. We demonstrate that we achieve statistically significant improvements over the baseline network. Furthermore, our results reveal that the XGBoost regressor and transformer outperform traditional feed-forward neural networks in this task. We make all our code and results available online on https://github.com/wzaielamri/Optimizing_BioTac_Simulation.

Wadhah Zai El Amri, Nicolás Navarro-Guerrero

Training machine learning models for robotic tactile sensing requires vast amounts of data, yet obtaining realistic interaction data remains a challenge due to physical complexity and variability. Simulating tactile sensors is thus a crucial step in accelerating progress. This paper presents SPLIT, a novel method for simulating image-based tactile sensors, with a primary focus on the DIGIT sensor. Central to our approach is a latent space arithmetic strategy that explicitly disentangles contact geometry from sensor-specific optical properties. Unlike methods that require recalibration for every new unit, this disentanglement allows SPLIT to adapt to diverse DIGIT backgrounds and even transfer data to distinct sensors like the GelSight R1.5 without full model retraining. Beyond this adaptability, our approach achieves faster inference speeds than existing alternatives. Furthermore, we provide a calibrated finite element method (FEM) soft-body mesh simulation with variable resolution, offering a tunable trade-off between speed and fidelity. Additionally, our algorithm supports bidirectional simulation, allowing for both the generation of realistic images from deformation meshes and the reconstruction of meshes from tactile images. This versatility makes SPLIT a valuable tool for accelerating progress in robotic tactile sensing research.

Wadhah Zai El Amri, Malte Kuhlmann, Nicolás Navarro-Guerrero

Tactile perception is essential for human interaction with the environment and is becoming increasingly crucial in robotics. Tactile sensors like the BioTac mimic human fingertips and provide detailed interaction data. Despite its utility in applications like slip detection and object identification, this sensor is now deprecated, making many valuable datasets obsolete. However, recreating similar datasets with newer sensor technologies is both tedious and time-consuming. Therefore, adapting these existing datasets for use with new setups and modalities is crucial. In response, we introduce ACROSS, a novel framework for translating data between tactile sensors by exploiting sensor deformation information. We demonstrate the approach by translating BioTac signals into the DIGIT sensor. Our framework consists of first converting the input signals into 3D deformation meshes. We then transition from the 3D deformation mesh of one sensor to the mesh of another, and finally convert the generated 3D deformation mesh into the corresponding output space. We demonstrate our approach to the most challenging problem of going from a low-dimensional tactile representation to a high-dimensional one. In particular, we transfer the tactile signals of a BioTac sensor to DIGIT tactile images. Our approach enables the continued use of valuable datasets and data exchange between groups with different setups.

Wadhah Zai El Amri, Malte Kuhlmann, Nicolás Navarro-Guerrero

Tactile perception is essential for human interaction with the environment and is becoming increasingly crucial in robotics. Tactile sensors like the BioTac mimic human fingertips and provide detailed interaction data. Despite its utility in applications like slip detection and object identification, this sensor is now deprecated, making many existing datasets obsolete. This article introduces a novel method for translating data between tactile sensors by exploiting sensor deformation information rather than output signals. We demonstrate the approach by translating BioTac signals into the DIGIT sensor. Our framework consists of three steps: first, converting signal data into corresponding 3D deformation meshes; second, translating these 3D deformation meshes from one sensor to another; and third, generating output images using the converted meshes. Our approach enables the continued use of valuable datasets.

Ziteng Li, Malte Kuhlmann, Ilana Nisky et al.

Compliance is a critical parameter for describing objects in engineering, agriculture, and biomedical applications. Traditional compliance detection methods are limited by their lack of portability and scalability, rely on specialized, often expensive equipment, and are unsuitable for robotic applications. Moreover, existing neural network-based approaches using vision-based tactile sensors still suffer from insufficient prediction accuracy. In this paper, we propose two models based on Long-term Recurrent Convolutional Networks (LRCNs) and Transformer architectures that leverage RGB tactile images and other information captured by the vision-based sensor GelSight to predict compliance metrics accurately. We validate the performance of these models using multiple metrics and demonstrate their effectiveness in accurately estimating compliance. The proposed models exhibit significant performance improvement over the baseline. Additionally, we investigated the correlation between sensor compliance and object compliance estimation, which revealed that objects that are harder than the sensor are more challenging to estimate.

Josip Josifovski, Shangding Gu, Mohammadhossein Malmir et al.

Domain randomization has emerged as a fundamental technique in reinforcement learning (RL) to facilitate the transfer of policies from simulation to real-world robotic applications. Many existing domain randomization approaches have been proposed to improve robustness and sim2real transfer. These approaches rely on wide randomization ranges to compensate for the unknown actual system parameters, leading to robust but inefficient real-world policies. In addition, the policies pretrained in the domain-randomized simulation are fixed after deployment due to the inherent instability of the optimization processes based on RL and the necessity of sampling exploitative but potentially unsafe actions on the real system. This limits the adaptability of the deployed policy to the inevitably changing system parameters or environment dynamics over time. We leverage safe RL and continual learning under domain-randomized simulation to address these limitations and enable safe deployment-time policy adaptation in real-world robot control. The experiments show that our method enables the policy to adapt and fit to the current domain distribution and environment dynamics of the real system while minimizing safety risks and avoiding issues like catastrophic forgetting of the general policy found in randomized simulation during the pretraining phase. Videos and supplementary material are available at https://safe-cda.github.io/.

Lasse Emil R. Bonner, Daniel Daugaard Buhl, Kristian Kristensen et al.

Multimodal object recognition is still an emerging field. Thus, publicly available datasets are still rare and of small size. This dataset was developed to help fill this void and presents multimodal data for 63 objects with some visual and haptic ambiguity. The dataset contains visual, kinesthetic and tactile (audio/vibrations) data. To completely solve sensory ambiguity, sensory integration/fusion would be required. This report describes the creation and structure of the dataset. The first section explains the underlying approach used to capture the visual and haptic properties of the objects. The second section describes the technical aspects (experimental setup) needed for the collection of the data. The third section introduces the objects, while the final section describes the structure and content of the dataset.

Tobias Hinz, Nicolás Navarro-Guerrero, Sven Magg et al.

Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional representation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher-dimensional data. We compare this approach with the standard procedure of optimizing the hyperparameters only on the original input. We perform experiments with various state-of-the-art hyperparameter optimization algorithms such as random search, the tree of parzen estimators (TPEs), sequential model-based algorithm configuration (SMAC), and a genetic algorithm (GA). Our experiments indicate that it is possible to speed up the optimization process by using lower-dimensional data representations at the beginning, while increasing the dimensionality of the input later in the optimization process. This is independent of the underlying optimization procedure, making the approach promising for many existing hyperparameter optimization algorithms.